Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 7 Learning parameters of DNN

From: Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification

 

Value

Batch size

128

Learning rate of Bernoulli-Bernoulli RBM

0.02

Learning rate of Gaussian-Bernoulli RBM

0.002

Weight decay

0.0002

Number of iterations in pre-training

50

number of iterations in fine-tuning

100

Back to article page